Bayesian estimation of adaptive bandwidth matrices in multivariate kernel density estimation

被引：49

作者：

Zougab, Nabil ^{[1
,2
]}

Adjabi, Smail ^{[2
]}

Kokonendji, Celestin C. ^{[3
]}

机构：

[1] Univ Tizi Ouzou, Tizi Ouzou, Algeria

[2] LAMOS, Lab Modelling & Optimizat Syst, Bejaia, Algeria

[3] Univ Franche Comte, Lab Math Besancon, UMR CNRS UFC 6623, F-25030 Besancon, France

来源：

COMPUTATIONAL STATISTICS & DATA ANALYSIS | 2014年 / 75卷

关键词：

Bandwidth matrix selection; Integrated squared error; Inverse Wishart distribution; Loss function; Plug-in; Smoothed cross-validation; DISCRETE TRIANGULAR DISTRIBUTIONS; CENSORED-DATA; SELECTION; EXTENSIONS;

D O I：

10.1016/j.csda.2014.02.002

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Bandwidth selection in multivariate kernel density estimation has received considerable attention. In addition to classical methods of bandwidth selection, such as plug-in and cross-validation methods, Bayesian approaches have also been previously investigated. Bayesian estimation of adaptive bandwidth matrices in multivariate kernel density estimation is investigated, when the quadratic and entropy loss functions are used. Under the quadratic loss function, the proposed method is evaluated through a simulation study and two real data sets, which were already discussed in the literature. For these real-data applications, very interesting advantages of the proposed method are pointed out. (C) 2014 Elsevier B.V. All rights reserved.

引用

页码：28 / 38

页数：11

共 20 条

[11]

Press S.J., 1985, APPL MULTIVARIATE AN

[12] On locally adaptive density estimation [J].

Sain, SR ;

Scott, DW .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1996, 91 (436) :1525-1534

[13] CROSS-VALIDATION OF MULTIVARIATE DENSITIES [J].

SAIN, SR ;

BAGGERLY, KA ;

SCOTT, DW .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1994, 89 (427) :807-817

[14] Multivariate locally adaptive density estimation [J].

Sain, SR .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2002, 39 (02) :165-186

[15]

WAND MP, 1994, COMPUTATION STAT, V9, P97

[16] ESTIMATION OF A COVARIANCE-MATRIX USING THE REFERENCE PRIOR [J].

YANG, RY ;

BERGER, JO .

ANNALS OF STATISTICS, 1994, 22 (03) :1195-1211

[17] A Bayesian approach to bandwidth selection for multivariate kernel density estimation [J].

Zhang, Xibin ;

King, Maxwell L. ;

Hyndman, Rob J. .

COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2006, 50 (11) :3009-3031

[18] Adaptive smoothing in associated kernel discrete functions estimation using Bayesian approach [J].

Zougab, N. ;

Adjabi, S. ;

Kokonendji, C. C. .

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2013, 83 (12) :2219-2231

[19] Binomial kernel and Bayes local bandwidth in discrete function estimation [J].

Zougab, N. ;

Adjabi, S. ;

Kokonendji, C. C. .

JOURNAL OF NONPARAMETRIC STATISTICS, 2012, 24 (03) :783-795

[20] A bayesian approach to bandwidth selection in univariate associate kernel estimation [J].

Zougab N. ;

Adjabi S. ;

Kokonendji C.C. .

Journal of Statistical Theory and Practice, 2013, 7 (1) :8-23

← 1 2 →